Yutian Chen Email & Phone Number

Durham, NC, US

United States

• Collaborate with genome consortium researchers to evaluate model performance in predicting enhancer activities on starr-seq.
• Compared custom vs standard loss, biased vs unbiased downsampling, and convolution layers vs attention layers on correlation coefficient and MSE by benchmarked leave-one-chromosome-out testing.
• Conducted in silico analysis of motif interactions on experimental and simulated data to replicate real biological experiment.
• Tested predicted variants on cCRE chunks and assisted with sanity check.
• Collaborated in Git and managed computational tasks in HPC environment using SLURM.

Hong Kong SAR

• Teach 2 local students Mandarin for 2 hours per week
• Manage behaviors and explain complex language concepts to 12-year-old students
• Assisted students with getting excellent scores in Mandarin speaking and writing exams

Hong Kong SAR

• Large Language Model on Genomic Data (2023)Programmed in Python
• Applied BERT model to the self-supervised pre-training of Single-nucleotide polymorphism data
• Applied Transformer to drug smiles embedding
• Utilized trained model to downstream task of drug efficiency prediction on inhibitory concentration (IC50)
• Collaborated with team of three by managing deadline workflowAI Method for Drug Interaction Detection (2022-2023) Programmed in Python and Neo4j
• Collaborated to collect drug interaction data from authoritative drug databases and data wrangling

Hong Kong SAR

• Data Analytics Intern
• Collected raw data of US student housings around target universities by scrapping and researching investment offering memorandums
• Built and trained XGB model to predict exact bedroom mixture and total bed number for certain student housing.
• Achieved 1% error rate in total bed number prediction.
• Translate complex concept in data science into implications for business

Hong Kong SAR

• Internal Audit Intern
• Engaged in data management, wrangling, and sampling for audit analysis using Python
• Built an automated program for audit sampling using VBA and generalized it in audit team
• Designed a Python script to simulate audit workforce plan and provided actionable advice for future hiring timeline
• Participated in NLP project by analyzing company’s risk incident data

Master'S Degree, Biostatistics

Relevant coursework includes: Introduction to Statistical Theory and Methods, Applied Biostatistics Methods, Introduction to the Practice.

Bachelor Of Science - Bs, Data Science, 3.76

Relevant coursework included: Calculus, Linear Algebra, Convex Optimization, Advanced Statistics, Python for Data Science, Data.

Exchange Program, Statistics

Relevant coursework included: Simulation, Statistical Design and Analysis of Experiments, Stochastic Process and Application